Workpiece surface flaw detection method and device

Abstract

The application provides a workpiece surface flaw detection method and device, which comprises the following steps: collecting first point cloud data of the surface of a workpiece to be detected during the transmission of the workpiece; performing differential calculation based on the first point cloud data and a pre-obtained vibration curve to obtain second point cloud data after the differential; performing discrete degree analysis according to the elevation value in the second point cloud data to determine whether the workpiece to be detected is a waste workpiece; and when the workpiece to be detected is not a waste workpiece, obtaining the surface flaw distribution of the workpiece to be detected based on the first point cloud data and third point cloud data of a standard workpiece collected in advance. The workpiece surface flaw detection method and device provided by the application can remove the influence of mechanical needles on data accuracy during the transmission of the workpiece, thereby improving the detection accuracy, and without physical modification, the cost increase is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of workpiece surface flaw detection, in particular to a workpiece surface flaw detection method and device. BACKGROUND

[0002] The surface quality of a steel plate is one of the main indicators of steel quality. During the production process of a steel plate, due to the influence of many technical factors such as raw materials, rolling process, system control, etc., cracks, scarring, holes, skin delamination, color spots, pitting and other defects often occur on the surface of the steel plate, which have different degrees of influence on the main characteristics of the steel plate such as wear resistance, fatigue resistance, corrosion resistance and electromagnetic properties.

[0003] In the production and manufacturing process, for a long time, the identification of defects on the surface of a steel plate has been completely completed by manual visual inspection. This method is labor-intensive, prone to missed detection and misdiagnosis. With the increase in production speed, visual inspection has become difficult to achieve the purpose of detection, and has gradually evolved into a form of sampling inspection. In the process of intelligent manufacturing transformation of enterprises, detection methods based on machine vision are emerging.

[0004] In existing machine vision detection technology, for the surface flaw detection of a steel plate, there are two technical approaches: 2D machine vision and 3D machine vision. Among them, 2D machine vision collects images and detects flaws based on color information on the surface of the steel plate. However, due to the small change in the color of the steel plate surface, the precision of flaw detection is low. Existing 3D machine vision detection technology ignores the influence of periodic mechanical vibration of the roller shaft of the conveying device during the conveying process of the steel plate. During the detection process, the vibration of the conveying device often causes distortion of the point cloud data collection, increasing the number of pseudo-flaws. Without data correction, direct detection model design will ultimately result in low detection accuracy and affect production. Although the roller shaft of the conveying device can be physically modified to reduce the influence of vibration, this will increase costs and still cannot eliminate the influence of vibration. SUMMARY

[0005] The present application aims to at least solve one of the technical problems existing in the prior art, and proposes a workpiece surface flaw detection method and device which can remove the influence of mechanical data accuracy during the transmission of the workpiece, thereby improving the detection accuracy, and without the need for physical modification, thereby avoiding the increase in costs.

[0006] To achieve the above-mentioned purpose, the present application provides a workpiece surface flaw detection method, comprising:

[0007] In the process of conveying the workpiece to be detected, first point cloud data of a surface of the workpiece to be detected is collected; the first point cloud data includes coordinate values corresponding to different positions of the surface of the workpiece to be detected in a conveying direction, coordinate values corresponding to different positions on a longitudinal section of the workpiece to be detected, and elevation values corresponding to different positions of the surface of the workpiece to be detected in the conveying direction;

[0008] Based on the first point cloud data and a pre-obtained vibration curve, difference calculation is performed to obtain second point cloud data after difference; the vibration curve represents the corresponding relationship between different positions of a surface of a standard workpiece in a conveying direction and elevation values;

[0009] According to the elevation values in the second point cloud data, discrete degree analysis is performed to determine whether the workpiece to be detected is a discarded workpiece;

[0010] When the workpiece to be detected is not a discarded workpiece, based on the second point cloud data and pre-collected elevation values of the standard workpiece, surface defect distribution of the workpiece to be detected is obtained.

[0011] Optionally, obtaining the vibration curve comprises:

[0012] Collecting third point cloud data of the standard workpiece;

[0013] Performing dimension reduction processing on the third point cloud data to convert the elevation values in the third point cloud data into modes of elevation values in a y-axis direction, to obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to a longitudinal section of the standard workpiece;

[0014] According to the fourth point cloud data and the elevation values of the standard workpiece in a static state, difference calculation is performed to obtain fifth point cloud data after difference;

[0015] According to the fifth point cloud data, the least square method is used to calculate the vibration curve.

[0016] Optionally, according to the elevation values in the second point cloud data, discrete degree analysis is performed to determine whether the workpiece to be detected is a discarded workpiece, which comprises:

[0017] Calculating a variance value of the elevation values in the second point cloud data, and when the variance value is greater than a preset threshold value, determining that the workpiece to be detected is a discarded workpiece;

[0018] When the variance value is less than or equal to the preset threshold value, it is determined that the workpiece to be detected is not a discarded workpiece.

[0019] Optionally, based on the second point cloud data and pre-collected elevation values of the standard workpiece, surface defect distribution of the workpiece to be detected is obtained, which comprises:

[0020] differencing the elevation value in the second point cloud data with the elevation value of the standard workpiece, to obtain sixth point cloud data after difference;

[0021] mapping according to the sixth point cloud data, to convert into a depth image;

[0022] analyzing the depth image to obtain the surface flaw distribution of the workpiece to be detected.

[0023] Optionally, the analyzing the depth image to obtain the surface flaw distribution of the workpiece to be detected comprises:

[0024] analyzing the depth image based on a neural network to obtain the surface flaw distribution of the workpiece to be detected.

[0025] As another technical solution, the workpiece surface flaw detection device provided by the application comprises:

[0026] a collection module, configured to collect first point cloud data of a surface of a workpiece to be detected in a process of conveying the workpiece to be detected; the first point cloud data comprises coordinate values corresponding to different positions of the surface of the workpiece to be detected in a conveying direction, coordinate values corresponding to different positions of a longitudinal section of the workpiece to be detected, and elevation values corresponding to different positions of the surface of the workpiece to be detected in the conveying direction;

[0027] a first difference module, configured to perform difference calculation based on the first point cloud data and a pre-obtained vibration curve to obtain second point cloud data after difference; the vibration curve represents a corresponding relationship between different positions of a standard workpiece in the conveying direction and elevation values;

[0028] a judgment module, configured to perform discrete degree analysis according to the elevation value in the second point cloud data, to determine whether the workpiece to be detected is a discarded workpiece; and

[0029] an analysis module, configured to, when the workpiece to be detected is not a discarded workpiece, obtain a surface flaw distribution of the workpiece to be detected based on the second point cloud data and pre-collected elevation values of the standard workpiece.

[0030] Optionally, the collection module is further configured to collect third point cloud data of the standard workpiece;

[0031] The workpiece surface flaw detection device further comprises:

[0032] a calculation module, configured to perform dimension reduction processing on the third point cloud data, to convert the elevation value in the third point cloud data into a mode of the elevation value in a y-axis direction, to obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to a longitudinal section of the standard workpiece.

[0033] The second difference module is configured to perform difference calculation on the fourth point cloud data and the elevation value of the standard workpiece in a static state to obtain fifth point cloud data after difference calculation.

[0034] The calculation module is further configured to calculate the vibration curve by using a least square method according to the fifth point cloud data.

[0035] Optionally, the analysis module is further configured to calculate a variance value of the elevation value in the second point cloud data, and determine that the workpiece is a discarded workpiece when the variance value is greater than a preset threshold value, and determine that the workpiece is not a discarded workpiece when the variance value is less than or equal to the preset threshold value.

[0036] Optionally, the analysis module is further configured to perform difference calculation on the elevation value in the second point cloud data and the elevation value of the standard workpiece to obtain sixth point cloud data after difference calculation, perform mapping on the sixth point cloud data to convert the sixth point cloud data into a depth image, and analyze the depth image to obtain a surface flaw distribution of the workpiece to be detected.

[0037] Optionally, the analysis module is further configured to analyze the depth image based on a neural network to obtain the surface flaw distribution of the workpiece to be detected.

[0038] The present application has the following advantages:

[0039] In the technical scheme of the workpiece surface flaw detection method and device provided by the embodiment of the present application, the high-precision point cloud data after vibration removal is obtained by performing difference calculation based on the first point cloud data and the vibration curve obtained in advance, the influence of the data accuracy of the mechanical needle in the process of transmitting the workpiece can be removed, so that the detection accuracy can be improved, and physical modification is not required, so that cost increase is avoided. At the same time, by analyzing the discrete degree of the elevation value in the second point cloud data, it is determined whether the workpiece to be detected is a discarded workpiece, the discarded workpiece can be quickly screened, and the discarded workpiece with large surface fluctuation and many flaw distributions can be removed, so that the detection efficiency can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 The flowchart of the workpiece surface flaw detection method provided by the embodiment of the present application is shown in the figure;

[0041] Figure 2 The flowchart of the method for obtaining the vibration curve used in the embodiment of the present application is shown in the figure;

[0042] Figure 3 The flowchart of step S4 of the workpiece surface flaw detection method provided by the embodiment of the present application is shown in the figure;

[0043] Figure 4A principle block diagram of the workpiece surface flaw detection device provided by the embodiment of the present application is shown in FIG. 1.

[0044] Figure 5 Another principle block diagram of the workpiece surface flaw detection device provided by the embodiment of the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0045] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0046] The shapes and sizes of the components in the drawings do not reflect true proportions, and the purpose is only to facilitate the understanding of the contents of the embodiments of the present application.

[0047] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood as the common meanings thereof by those skilled in the art. The terms "first", "second" and similar words used in the present disclosure do not represent any order, number or importance, but are only used to distinguish different components. Similarly, the terms "one", "an" or "the" and similar words do not represent a quantity limitation, but represent the existence of at least one. The terms "include" or "contain" and similar words mean that the elements or objects before the words cover the elements or objects listed after the words and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "up", "down", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute positions of the described objects change, the relative positional relationships may also change accordingly.

[0048] The embodiments of the present disclosure are not limited to the embodiments shown in the drawings, but include modifications of configurations formed based on manufacturing processes. Therefore, the regions exemplified in the drawings have a schematic property, and the shapes of the regions shown in the drawings exemplify specific shapes of the regions of the elements, but are not intended to be restrictive.

[0049] Please refer to Figure 1 The workpiece surface flaw detection method provided by the embodiment of the present application comprises:

[0050] S1, collecting first point cloud data of the surface of the workpiece to be detected in the process of conveying the workpiece to be detected;

[0051] The first point cloud data is points(x, y, z), wherein the x value is a coordinate value corresponding to different positions of the surface of the workpiece to be detected in the conveying direction; the y value is a coordinate value corresponding to different positions on the longitudinal section (i.e., a section in a direction perpendicular to the surface of the workpiece to be detected) of the workpiece to be detected; and the z value is an elevation value (a distance of a point to an absolute datum along a plumb line direction) corresponding to different positions of the surface of the workpiece to be detected in the conveying direction.

[0052] The workpiece to be detected is, for example, a steel plate or other workpiece that needs to be detected for surface defects.

[0053] S2, based on the first point cloud data and a pre-obtained vibration curve, differential calculation is performed to obtain second point cloud data after difference; the vibration curve represents a corresponding relationship between different positions of the surface of a standard workpiece in the conveying direction and the elevation value;

[0054] The standard workpiece is a workpiece with no surface defects.

[0055] Based on the data difference of the vibration curve, high-precision point cloud data after vibration elimination, i.e., point cloud data after elimination of the influence of vibration (the second point cloud data) can be calculated.

[0056] In the functional relationship of the vibration curve, x is a coordinate value corresponding to different positions of the surface of the workpiece to be detected in the conveying direction, and is a variable; g(x) is an elevation value, and is a dependent variable. The second point cloud data is points(x, y, z'), wherein z' = z-g(x).

[0057] S3, according to the elevation value in the second point cloud data, a discrete degree analysis is performed to determine whether the workpiece to be detected is a scrap workpiece;

[0058] By performing the discrete degree analysis on the elevation value in the second point cloud data, the screening of the scrap workpiece can be quickly completed, and the scrap workpiece with large surface fluctuation and many defect distributions can be removed.

[0059] S4, when the workpiece to be detected is not a scrap workpiece, based on the second point cloud data and the elevation value of the standard workpiece pre-collected, a surface defect distribution of the workpiece to be detected is obtained.

[0060] Since the surface of the standard workpiece has no defects, the elevation values corresponding to different positions on the surface of the standard workpiece are fixed and unchangeable.

[0061] The workpiece surface flaw detection method provided by the embodiment of the application can obtain high-precision point cloud data after vibration by performing difference calculation based on the first point cloud data and the pre-obtained vibration curve, can remove the influence of the mechanical needle on data accuracy in the process of conveying the workpiece, and thus can improve the detection accuracy, and does not need to be physically modified, and thus will not increase the cost. Meanwhile, by performing discrete degree analysis according to the elevation value in the second point cloud data, it is determined whether the workpiece to be detected is a discarded workpiece, the discarded workpiece can be quickly screened, and the discarded workpiece with large surface fluctuation and many flaws is removed, and thus the detection efficiency can be improved.

[0062] In some optional embodiments, referring to Figure 2 , the vibration curve includes:

[0063] S21, collecting third point cloud data of a standard workpiece;

[0064] The third point cloud data is points(x1, y1, z1), wherein the x1 value is a coordinate value corresponding to different positions of the surface of the standard workpiece in the conveying direction; the y1 value is a coordinate value corresponding to different positions on the longitudinal section (i.e., a section in a direction perpendicular to the surface of the workpiece to be detected) of the standard workpiece; and the z1 value is an elevation value corresponding to different positions of the surface of the standard workpiece in the conveying direction.

[0065] S22, performing dimension reduction processing on the third point cloud data to convert the elevation value in the third point cloud data into a mode (i.e., a value with a clear concentration trend in statistical distribution, representing the general level of data) of the elevation value in the y-axis direction, to obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to the longitudinal section (i.e., a section in a direction perpendicular to the surface of the standard workpiece) of the standard workpiece.

[0066] The method of dimension reduction processing includes, for example:

[0067] Along the y-axis direction of the standard workpiece, the elevation values of different positions of the surface of the standard workpiece in the conveying direction are merged and calculated to take the z value corresponding to different x values on the surface of the standard workpiece as the mode of the elevation value in the y-axis direction, i.e., points(x1, y1, z1) is converted into points(x1, z1'), wherein z1'=mode(z) x＝x1 .

[0068] By performing dimension reduction processing on the third point cloud data, the slight vibration difference of different positions on a single roller shaft in the conveying device can be ignored, and thus the calculation pressure can be greatly reduced.

[0069] S23, performing difference calculation on the fourth point cloud data and the elevation value of the standard workpiece in the static state to obtain fifth point cloud data after difference.

[0070] The fifth point cloud data is points(x,z'), where z' = z - z0, z is the elevation value in the fourth point cloud data, and z0 is the elevation value of the standard workpiece in a static state.

[0071] S24. Based on the cloud data of point five above, the vibration curve g(x) above is obtained by calculating using the least squares method.

[0072] In some optional embodiments, the method for calculating the vibration curve g(x) using the least squares method includes:

[0073] Assume g(x) = θ0 + θ1x + ... + θ n x n

[0074] make

[0075] The sum of squared errors S is calculated as follows:

[0076] S=(X v θ-Y r ) T (X v θ-Y r );

[0077] in, Calculate and obtain the polynomial coefficient vector matrix Thus, the vibration curve g(x) can be obtained.

[0078] In some optional embodiments, step S3 above specifically includes:

[0079] Calculate the variance s of the elevation values ​​in the second point cloud data mentioned above. 2 At this variance value s 2 When the value exceeds the preset threshold thres, the workpiece to be inspected is determined to be a discarded workpiece; when the variance value s 2 If the value is less than or equal to the preset threshold thres, the workpiece to be tested is determined to be a discarded workpiece.

[0080] In some alternative embodiments, please refer to Figure 3 The above step S4 specifically includes:

[0081] S41. Perform a difference calculation between the elevation value in the second point cloud data and the elevation value of the standard workpiece to obtain the sixth point cloud data after the difference calculation.

[0082] S42. Map the cloud data from the sixth point and convert it into a depth image;

[0083] Mapping the sixth point cloud data points(x, y, δz) with the plane position (x, y) in points(x, y, z) as an index and the elevation value z as a characteristic value, to convert into a depth image;

[0084] S43, analyzing the above depth image to obtain the surface flaw distribution of the workpiece to be detected.

[0085] In some optional embodiments, the above depth image is analyzed based on a neural network to obtain the surface flaw distribution of the workpiece to be detected.

[0086] As another technical solution, please refer to Figure 4 The embodiment of the present application provides a workpiece surface flaw detection device, comprising:

[0087] The acquisition module 1 is used for acquiring first point cloud data of the surface of the workpiece to be detected during conveying the workpiece to be detected;

[0088] The first difference module 2 is used for performing difference calculation based on the first point cloud data and a pre-obtained vibration curve to obtain second point cloud data after difference; the vibration curve represents the corresponding relationship between different positions of a standard workpiece in the conveying direction and the elevation value;

[0089] The judgment module 3 is used for performing discrete degree analysis according to the elevation value in the second point cloud data to determine whether the workpiece to be detected is a discarded workpiece; and

[0090] The analysis module 4 is used for, when the workpiece to be detected is not a discarded workpiece, obtaining the surface flaw distribution of the workpiece to be detected based on the second point cloud data and the pre-acquired elevation value of the standard workpiece.

[0091] In some optional embodiments, please refer to Figure 5 The acquisition module 1 is also used for acquiring third point cloud data of the standard workpiece;

[0092] The workpiece surface flaw detection device further comprises:

[0093] The calculation module 5 is used for performing dimension reduction processing on the third point cloud data, converting the elevation value in the third point cloud data into the mode of the elevation value in the y-axis direction to obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to the longitudinal section of the standard workpiece;

[0094] The second difference module 6 is used for performing difference calculation according to the fourth point cloud data and the elevation value of the standard workpiece in the static state to obtain fifth point cloud data after difference;

[0095] The calculation module 5 is also used for calculating the vibration curve by using the least square method according to the fifth point cloud data.

[0096] In some optional embodiments, the determining module 3 is further configured to analyze the second point cloud data, and the analyzing module 4 is further configured to calculate a variance value of the elevation values in the second point cloud data, and determine that the workpiece is a discarded workpiece when the variance value is greater than a preset threshold value, and determine that the workpiece is not a discarded workpiece when the variance value is less than or equal to the preset threshold value.

[0097] In some optional embodiments, the analyzing module 4 is further configured to calculate the difference between the elevation values in the second point cloud data and the elevation values of a standard workpiece, calculate sixth point cloud data after the difference, map the sixth point cloud data, convert the sixth point cloud data into a depth image, and analyze the depth image to obtain the surface flaw distribution of the workpiece to be detected.

[0098] In some optional embodiments, the analyzing module 4 is further configured to analyze the depth image based on a neural network to obtain the surface flaw distribution of the workpiece to be detected.

[0099] The workpiece surface flaw detection device provided by the embodiments of the present application can obtain high-precision point cloud data after removing vibration by calculating the difference between the first point cloud data and the pre-obtained vibration curve, can remove the influence of the mechanical needle on the data accuracy in the process of transmitting the workpiece, and thus can improve the detection accuracy without physical modification, thereby avoiding cost increase. Meanwhile, the degree of dispersion of the elevation values in the second point cloud data is analyzed to determine whether the workpiece to be detected is a discarded workpiece, the discarded workpiece can be quickly screened, and the discarded workpiece with large surface fluctuation and many surface flaws can be removed, and thus the detection efficiency can be improved.

[0100] It can be understood that the above embodiments are only exemplary embodiments for illustrating the principles of the present application, and the present application is not limited thereto. Various modifications and improvements can be made by those skilled in the art without departing from the spirit and essence of the present application, and these modifications and improvements are also considered to be within the protection scope of the present application.

Claims

1. A method of detecting surface flaws of a workpiece, characterized by, Comprising: acquiring first point cloud data of a surface of a workpiece to be detected in a process of conveying the workpiece to be detected; the first point cloud data includes coordinate values corresponding to different positions of the surface of the workpiece to be detected in a conveying direction, coordinate values corresponding to different positions on a longitudinal section of the workpiece to be detected, and elevation values corresponding to different positions of the surface of the workpiece to be detected in the conveying direction; based on the first point cloud data and a pre-obtained vibration curve, difference calculation is performed to obtain second point cloud data after difference; the vibration curve represents the correspondence between different positions of the surface of a standard workpiece in the conveying direction and the elevation values; according to the elevation values in the second point cloud data, discrete degree analysis is performed to determine whether the workpiece to be detected is a discarded workpiece; when the workpiece to be detected is not a discarded workpiece, based on the second point cloud data and the elevation values of the standard workpiece pre-acquired, the surface defect distribution of the workpiece to be detected is obtained; obtaining the vibration curve includes: acquiring third point cloud data of the standard workpiece; dimension reduction processing is performed on the third point cloud data, the elevation values in the third point cloud data are converted into mode values of elevation values in the y-axis direction to obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to the longitudinal section of the standard workpiece; difference calculation is performed according to the fourth point cloud data and the elevation values of the standard workpiece in a static state to obtain fifth point cloud data after difference; the least square method is used to calculate the vibration curve according to the fifth point cloud data.

2. The method of claim 1, wherein The discrete degree analysis according to the elevation values in the second point cloud data to determine whether the workpiece to be detected is a discarded workpiece includes: calculating the variance value of the elevation values in the second point cloud data, when the variance value is greater than a preset threshold value, it is determined that the workpiece to be detected is a discarded workpiece; when the variance value is less than or equal to the preset threshold value, it is determined that the workpiece to be detected is not a discarded workpiece.

3. The method of claim 1, wherein The surface defect distribution of the workpiece to be detected is obtained based on the second point cloud data and the elevation values of the standard workpiece pre-acquired, which includes: difference calculation is performed on the elevation values in the second point cloud data and the elevation values of the standard workpiece to calculate sixth point cloud data after difference; mapping is performed according to the sixth point cloud data to convert into a depth image; the depth image is analyzed to obtain the surface defect distribution of the workpiece to be detected.

4. The method of claim 3, wherein The analysis of the depth image to obtain the surface defect distribution of the workpiece to be detected includes: the depth image is analyzed based on a neural network to obtain the surface defect distribution of the workpiece to be detected.

5. A workpiece surface flaw detection apparatus characterized by comprising: Comprising: an acquisition module, configured to acquire first point cloud data of a surface of a workpiece to be detected in a process of conveying the workpiece to be detected; the first point cloud data includes coordinate values corresponding to different positions of the surface of the workpiece to be detected in a conveying direction, coordinate values corresponding to different positions on a longitudinal section of the workpiece to be detected, and elevation values corresponding to different positions of the surface of the workpiece to be detected in the conveying direction; The first difference module is configured to perform difference calculation based on the first point cloud data and a pre-obtained vibration curve to obtain second point cloud data after difference calculation; the vibration curve represents a correspondence between different positions of a standard workpiece in a conveying direction and elevation values; The judgment module is configured to perform discrete degree analysis according to the elevation values in the second point cloud data to determine whether the workpiece to be detected is a discarded workpiece; The analysis module is configured to, when the workpiece to be detected is not a discarded workpiece, obtain a surface defect distribution of the workpiece to be detected based on the second point cloud data and pre-collected elevation values of the standard workpiece. The collection module is further configured to collect third point cloud data of the standard workpiece. The workpiece surface defect detection device further includes: The calculation module is configured to perform dimension reduction processing on the third point cloud data, convert the elevation values in the third point cloud data into modes of elevation values in a y-axis direction, and obtain fourth point cloud data after dimension reduction; the y-axis direction is parallel to a longitudinal section of the standard workpiece. The second difference module is configured to perform difference calculation according to the fourth point cloud data and elevation values of the standard workpiece in a static state to obtain fifth point cloud data after difference calculation. The calculation module is further configured to calculate the vibration curve by using a least square method according to the fifth point cloud data. The analysis module is further configured to calculate a variance value of the elevation values in the second point cloud data, determine that the workpiece is a discarded workpiece when the variance value is greater than a preset threshold value, and determine that the workpiece is not a discarded workpiece when the variance value is less than or equal to the preset threshold value.

6. The workpiece surface flaw detection apparatus of claim 5, wherein The analysis module is further configured to perform difference calculation on the elevation values in the second point cloud data and the elevation values of the standard workpiece to calculate sixth point cloud data after difference calculation, perform mapping according to the sixth point cloud data to convert the sixth point cloud data into a depth image, and analyze the depth image to obtain a surface defect distribution of the workpiece to be detected.

7. The workpiece surface flaw detection apparatus of claim 5, wherein The analysis module is further configured to analyze the depth image based on a neural network to obtain a surface defect distribution of the workpiece to be detected.

8. The workpiece surface flaw detection apparatus of claim 7, wherein, ​

Images